Filters








3,702 Hits in 10.6 sec

Exploiting Text Matching Techniques for Knowledge-Grounded Conversation

Yeonchan Ahn, Sang-Goo Lee, Jaehui Park
2020 IEEE Access  
To generate an informative and context-coherent response, it is important to conjugate dialogue context and external knowledge in a balanced manner.  ...  Knowledge-grounded conversation models aim at generating informative responses for the given dialogue context, based on external knowledge.  ...  However, they do not focus on how to model the context in a multi-turn dialogue setting, where they merely model a multi-turn dialogue as a single document.  ... 
doi:10.1109/access.2020.3007893 fatcat:jyu3rvorwjhbrfsjafnwct5eiu

What we need to learn if we want to do and not just talk

Rashmi Gangadharaiah, Balakrishnan Narayanaswamy, Charles Elkan
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)  
In task-oriented dialog, agents need to generate both fluent natural language responses and correct external actions like database queries and updates.  ...  We propose a hybrid model, where nearest neighbor is used to generate fluent responses and Sequence-to-Sequence (Seq2Seq) type models ensure dialogue coherency and generate accurate external actions.  ...  Conclusion and Future Work We demonstrated limitations of previous end-end dialog approaches and proposed variants to make them suitable for real world settings.  ... 
doi:10.18653/v1/n18-3004 dblp:conf/naacl/GangadharaiahNE18 fatcat:wm2btzvc75eu3gwhwfqvuwsn2i

Chat More If You Like: Dynamic Cue Words Planning to Flow Longer Conversations [article]

Lili Yao, Ruijian Xu, Chao Li, Dongyan Zhao, Rui Yan
2018 arXiv   pre-print
To this end, we present the multi-turn cue-words driven conversation system with reinforcement learning method (RLCw), which strives to select an adaptive cue word with the greatest future credit, and  ...  To build an open-domain multi-turn conversation system is one of the most interesting and challenging tasks in Artificial Intelligence.  ...  Specifically, we present the multi-turn cue-words driven conversation system with reinforcement learning (RLCw), which jointly models the cue word prediction and response generation in an end-to-end framework  ... 
arXiv:1811.07631v1 fatcat:hvzijxoaazh67hqv63smzoxvl4

Do You Ever Get Off Track in a Conversation? The Conversational System's Anatomy and Evaluation Metrics

Sargam Yadav, Abhishek Kaushik
2022 Knowledge  
This approach can help us to better understand the overall process of dialog system development, and future possibilities to enhance user experience.  ...  Conversational systems are now applicable to almost every business domain. Evaluation is an important step in the creation of dialog systems so that they may be readily tested and prototyped.  ...  The dialog manager also takes into account dialog history while selecting responses that feel more natural and user-friendly.  ... 
doi:10.3390/knowledge2010004 fatcat:brdrsquzf5eq3jg4cmzin6rkhm

Interactive Searching and Browsing of Video Archives: Using Text and Using Image Matching [chapter]

Alan F. Smeaton, Cathal Gurrin, Hyowon Lee
2006 Signals and Communication Technology  
The shot retrieval engine employed for Físchlár-TRECVid is based on a combination of query text matched against spoken dialogue combined with image-image matching where a still image (sourced externally  ...  The user of the system was allowed to choose which of the XM techniques were to be used for any given query.  ... 
doi:10.1007/978-3-540-33215-2_9 fatcat:prigexdutzatdnoi44w2wxqa74

Dynamically Retrieving Knowledge via Query Generation for informative dialogue response [article]

Zhongtian Hu, Yangqi Chen, Yushuang Liu, Lifang Wang
2022 arXiv   pre-print
In order to solve the problem, we design a knowledge-driven dialogue system named DRKQG (Dynamically Retrieving Knowledge via Query Generation for informative dialogue response).  ...  First, a time-aware mechanism is utilized to capture context information and a query can be generated for retrieving knowledge.  ...  Model Q F1 Q BLEU-1 Q BLEU- There will be 30 dialogue sessions used to test our system, and each dialogue session will not be less than 7 turns of dialogue.  ... 
arXiv:2208.00128v1 fatcat:2qf635nkhzh4jh5zw7hhwaq46y

Improving service matching and selection in ubiquitous computing environments: a user study

Jasper Lindenberg, Wouter Pasman, Kim Kranenborg, Joris Stegeman, Mark A. Neerincx
2006 Personal and Ubiquitous Computing  
This user study compares the newly developed service matcher system with a conventional system for identifying and selecting appropriate services.  ...  In large ubiquitous computing environments it is hard for users to identify and activate the electronic services that match their needs.  ...  Then, the Wizard of Oz prepares the agent and sends the interface to the user. The dialogue is logged for analyses The select interface. Users select an agent using a hierarchy containing all agents.  ... 
doi:10.1007/s00779-006-0066-7 fatcat:udw4yfxdcve3rngavvkql3lksm

CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases [article]

Tao Yu, Rui Zhang, He Yang Er, Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, Youxuan Jiang, Michihiro Yasunaga, Sungrok Shim (+9 others)
2019 arXiv   pre-print
We present CoSQL, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems.  ...  CoSQL includes three tasks: SQL-grounded dialogue state tracking, response generation from query results, and user dialogue act prediction.  ...  are given as part of the conversation history but we do not require a system to predict SQL queries for them.  ... 
arXiv:1909.05378v1 fatcat:6acielnwvvaptov5ipmnddrkwi

CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases

Tao Yu, Rui Zhang, Heyang Er, Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, Youxuan Jiang, Michihiro Yasunaga (+12 others)
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
We present CoSQL, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems.  ...  CoSQL includes three tasks: SQL-grounded dialogue state tracking, response generation from query results, and user dialogue act prediction.  ...  are given as part of the conversation history but we do not require a system to predict SQL queries for them.  ... 
doi:10.18653/v1/d19-1204 dblp:conf/emnlp/YuZELXPLTSLJYSC19 fatcat:k2hth3eegfaerkb2hycu4tehgi

How do you Converse with an Analytical Chatbot? Revisiting Gricean Maxims for Designing Analytical Conversational Behavior [article]

Vidya Setlur, Melanie Tory
2022 arXiv   pre-print
system responses.  ...  We also draw inspiration from natural language interfaces for data exploration to support ambiguity and intent handling.  ...  For example, for the query, "which products are doing well?"  ... 
arXiv:2203.08420v1 fatcat:ozi7cyobufat5j3olwivq2kxei

Multi-turn Response Selection using Dialogue Dependency Relations [article]

Qi Jia, Yizhu Liu, Siyu Ren, Kenny Q. Zhu, Haifeng Tang
2020 arXiv   pre-print
Multi-turn response selection is a task designed for developing dialogue agents. The performance on this task has a remarkable improvement with pre-trained language models.  ...  However, these models simply concatenate the turns in dialogue history as the input and largely ignore the dependencies between the turns.  ...  Acknowledgement This research was supported by the SJTU-CMBCC Joint Research Scheme, SJTU Medicine-Engineering Cross-disciplinary Research Scheme, and NSFC grant 91646205.  ... 
arXiv:2010.01502v1 fatcat:5vlkd5ezivb6blhcrmarz7ho6i

How do you Converse with an Analytical Chatbot? Revisiting Gricean Maxims for Designing Analytical Conversational Behavior

Vidya Setlur, Melanie Tory
2022 CHI Conference on Human Factors in Computing Systems  
(a) A Slack chatbot showing an interactive message with a drop-down menu to help a user refine a previous response within the conversation thread.  ...  Follow-up questions and feedback from the chatbot encourage conversational behavior.  ...  For example, for the query, "which products are doing well?"  ... 
doi:10.1145/3491102.3501972 fatcat:jmylakmeqzcnljlvx6sfuz4che

CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset [article]

Qi Zhu, Kaili Huang, Zheng Zhang, Xiaoyan Zhu, Minlie Huang
2020 arXiv   pre-print
It contains 6K dialogue sessions and 102K utterances for 5 domains, including hotel, restaurant, attraction, metro, and taxi.  ...  We also provide a user simulator and several benchmark models for pipelined task-oriented dialogue systems, which will facilitate researchers to compare and evaluate their models on this corpus.  ...  We would like to thank THUNUS NExT Joint-Lab for the support. We would also like to thank Ryuichi Takanobu and Fei Mi for their constructive comments.  ... 
arXiv:2002.11893v2 fatcat:u72d2lzzqfeijpcqvacvgfme2y

Challenges in Building Intelligent Open-domain Dialog Systems [article]

Minlie Huang, Xiaoyan Zhu, Jianfeng Gao
2020 arXiv   pre-print
The works we select to present here is based on our unique views and are by no means complete.  ...  Unlike traditional task-oriented bots, an open-domain dialog system aims to establish long-term connections with users by satisfying the human need for communication, affection, and social belonging.  ...  There is a short review on deep retrieval-based dialogue systems [10] where the authors discussed existing work with respect to single-turn matching models, multi-turn matching models, and ensemble models  ... 
arXiv:1905.05709v3 fatcat:vdibhr4sobgufgcab2cyfyg7wy

Advances in Multi-turn Dialogue Comprehension: A Survey [article]

Zhuosheng Zhang, Hai Zhao
2021 arXiv   pre-print
Among these studies, the fundamental yet challenging type of task is dialogue comprehension whose role is to teach the machines to read and comprehend the dialogue context before responding.  ...  In this paper, we review the previous methods from the technical perspective of dialogue modeling for the dialogue comprehension task.  ...  Second, response candidates on the test set are collected by using the last turn as the query to retrieve 10 response candidates and labeled by humans.  ... 
arXiv:2110.04984v2 fatcat:4i4svd2oyvdhhasqx2ungtppue
« Previous Showing results 1 — 15 out of 3,702 results